• 간호행정학회지
• /
• 제11권4호
• /
• pp.401-414
• /
• 2005

Purpose: This study was to evaluate the utilization of health care service and to provide supportive data for health care policy making in one urban area in Korea. Method: This study tested the significance of public health service using the database of an university hospital and public health center from Feb. 2000 to Dec. 2004. Data were analyzed by multidimensional analysis and data mining technique and produced the information on the classification of utilization characteristics by main disease and the total cost of use and disease association with the users of the public health center. Results: The Results were as follows: 1) Top 10 diseases in the area accounted for 22.4% of total frequency for the most recent 5 years in university hospital, while 59.0% in public health center. 2) There were significant correlations between university hospital and public health center user's insurance type and place of residence: It showed higher use of public health center for free service beneficiaries residing in Seoul than residents in nearby or local area. The medical insurance types for hospital users were more various than those for public health center users. 3) The use of hospital for patients of hypertension, diabetes mellitus and hyperlipidemia was tended to concentrate in mostly autumn and winter since August 2000, while the cost of using public health center for those patients has been steadily reduced since July 2000. 4) As a result of cluster analysis, there were classified into three homogeneous groups according to the total cost of using public health service, age, and the frequency of use. 5) The association analysis on patients with chronic disease in public health center produced a detailed information on accompanying diseases related to the incidence rate of disease of high frequency due to aging, information on drug abuse and immune disease. Conclusion: The health care policy for local community should be evaluated continuously. And the policy to build an integrated data warehousing by public health indicator system and to enhance the faithfulness of data is required.

• 한국조경학회지
• /
• 제25권4호
• /
• pp.1-17
• /
• 1998

Most of the tourist resort facilities in our country cannot be used in the winter season, and only a few spa resorts and sky resorts are available in the winter. To ameliorate this problem, various types of winter resort facilities have been constructed since 1970s and the massive development of winter resort facilities changed the resort market from a seller's market to a buyer's market. There has been however,few researches on marketing strategies for winter resorts, and there is a growing need for a rational method to maximize tourists' satisfaction and developers'profit at the same time. This research aims to develop a positining strategy to engance the marketability of winter resorts by classifying the resort market with the self-image types of users, and by analyzing the structure of the market, users' preferences, and locational factors. A survey was conducted with cases of Yong-Pyung resort, Mu-Ju resort, Alps resort, Bears resort, Back-Am spa resort, Su-An-Bo spa resort, and I-Chon spa resort. A list of questions in five categories -- similarity, characteristics, preferences, self-image, and personal characteristics of the respondents -- was constructed and tested. Among the 750 copies of questionnaire distributed, 700 were returned by only 378 were analyzed after screening missing or reckless answers. The statistical analysis of the data were conducted using techniques of correlation analysis, frequency analysis, factor analysis. Factor analysis and cluster analysis were used to group the cluster of self-image and a discriminant analysis were used to confirm this classification. The demographical characteristics were identified by frequency analysis, and resorts attributes were analyzed by oneway ANOVA analysis. Multidimensional scaling methods such as KYST, PROFIT, and PREFMAP were used for the positioning strategy.

• 한국전문물리치료학회지
• /
• 제21권4호
• /
• pp.56-66
• /
• 2014

For maintaining adequate psychometric properties when reducing the number of items from an instrument, item level psychometrics is crucial. Strategies such as low item correlation or factor loadings, using classical test theory, have traditionally been advocated. The purpose of this study is to describe the development of a new short form assessing the impact of low back pain on physical activity. Rasch measurement model has been applied to the International Classification of Functioning, Disability and Health Activity Measure (ICF-AM). One hundred and one individuals with low back pain aged 19-89 years (mean age: $48.1{\pm}17.3$) who live in the community were participated in the study. Twenty-seven items of lifting/carrying construct of the ICF-AM were analyzed. Ten items were selected from the construct to create a short form. Item elimination criteria include: 1) high or low mean square (out of the range: .6-1.4 for the fit statistics), 2) similar item calibrations to adjacent items, 3) person separation value, and item-person map for potential gap in person ability continuum. All 10 items of the short form fit to the Rasch model except one item (i.e., carrying toddler on back). Despite its high infit and outfit statistics (1.90/2.17), the item had to be reinstated due to potential gaps at the upper extreme of person ability level. The short form had a slightly better spread of person ability continuum compared to the entire set of item. The created short form separated individuals with low back pain into nearly 4 groups, while the entire set of items separated the individuals into 6 groups. The findings prompted multidimensional models for better explanation of the lifting/carrying domain. The item level psychometrics based on the Rasch model can be useful in developing short forms with rationally retained items.

• 한국간호교육학회지
• /
• 제10권1호
• /
• pp.84-93
• /
• 2004

Purpose: This study was conducted to investigate the subjective degree of fatigue, the degree of fatigue depending on constitution, and the factors related to fatigue in middle-aged women. Method: Data were collected from 51 patients, registered at Oriental Medicine Hospital in J-city and K-city respectively. The instrument used in this study were the Multidimensional Assessment of Fatigue and the Questionnaire of Sasang Constitution Classification Ⅱ. Data analysis was done SPSS Result: The characteristics of constitution in middle-aged women could be divided into three: twenty six people of Soeumin, thirteen people of Taeumin, and twelve people of Soyangin. The degree of fatigue in middle-aged women: the average score 30.61 out of the total score 40. Subdivision of fatigue scores: common fatigue degree 7.71, distress due to fatigue 7.67, degree of daily activity fatigue 7.43, and fatigue frequency in the previous week 7.84. There were significant differences in the degree of fatigue depending on constitution in middle-aged women(p=.033). This study revealed weight, exercise, and drinking are important factors that can exert influence on the degree of fatigue. Also, there was a big difference in the degree of fatigue depending on constitution. Conclusion: In conclusion, fatigue is one of the difficult problems with middle-aged women. And this study revealed that change in the weight(especially loss of weight), physical exercise, and drinking are important factors that can exert influence on the degree of fatigue. Also, there was a big difference in the degree of fatigue depending on constitution. Therefore it is necessary to develop Korean nursing intervention to providing an appropriate environment where there is the harmony of the dual principles of the negative and positive, and patients can be taken care of properly.

• 한국주거학회논문집
• /
• 제23권4호
• /
• pp.59-67
• /
• 2012

Developing the modern design of Hanok and providing support for the commercialization model development in recent years propelled by the New Hanok Support Strategies of the central government in conjunction with the New Hanok revitalization related projects reflecting local goverments. New Hanok revitalization, the rekindling and revaluing of human behaviors and interests in local goverments following the social and cultural changes of the past decades, has emeraged as an increasingly traditional area of concerning in New Hanok planning. In this paper we attempt to this discussion by describing recent projects in New Hanok revitalization in Jeollanam-do Province. Therefore, this study aims to examine the classification of compound knowledges based multidimensional relationship by using Self-Organizing Maps (SOM). SOM is an unsupervised learning neural network model for the analysis of high-dimensional input data. By using SOM, we were able to create a cluster map reflecting the characteristics of the New Hanok. In this case the pattern of the preference data was easily understood by visual analysis. Liking for compound knowledge deduced from this data was classified into 8 categories according to the compound knowledge properties of New Hanok. As a result, a systematic approach for analysis the characteristics of individual family and living environment of New Hanoks and 10 space usage patterns the changes in some aspects of New Hanok.

• 한국정보통신학회논문지
• /
• 제13권10호
• /
• pp.2180-2188
• /
• 2009

본 논문은 지능로봇의 동작을 제어하기 위해 비전기반의 실시간 수신호를 PCA 및 BP 알고리즘을 이용한 인식시스템을 제안하였다. 수신호 인식은 PCA 알고리즘을 이용한 전처리 단계와 BP 알고리즘을 이용한 인식의 두 단계로 구성한다. PCA 알고리즘은 데이터 분석을 위해 다차원 데이터 집합을 보다 낮은 차원으로 감소시키기 위해 사용되는 기술로 주어진 수신호의 특징인 투영 벡터를 계산하기 위하여 적용되었고, BP 알고리즘은 병렬 구조를 가지고 있으므로 병렬 분산처리가 가능하고, 처리 속도가 빠르므로 PCA로부터 훈련된 고유 수신호를 학습시켜 수신호를 실시간으로 인식한다. 실험에서는 10종류의 수신호를 PCA 알고리즘만을 사용한 경우와 제안한 PCA 및 BP 알고리즘을 사용한 경우와 인식률을 비교하여 제안한 알고리즘이 우수하다는 것을 보였다.

• Physical Therapy Rehabilitation Science
• /
• 제8권3호
• /
• pp.125-133
• /
• 2019

Objective: To compare the postural control between non-specific chronic low back pain (NSCLBP) subgroups and healthy people during dynamic balance performance using a modified Star Excursion Balance Test (mSEBT). Design: Cross-sectional study. Methods: Eighteen NSCLBP subjects (9 active extension pattern [AEP], 9 flexion pattern [FP]), and 10 healthy controls were enrolled in this study. All subjects performed mSEBT on their dominant leg on a force plate. Normalized reach distance and balance parameters, including the center of pressure (COP) displacement and velocity, were recorded. Results: There were significant differences in mean reach distances in both posterolateral and posteromedial (PM) reach directions between AEP and healthy subjects (p<0.001) and between FP and healthy subjects (p<0.001). However, there were no significant differences among the three groups in the anterior reach direction. Also, the results showed no significant differences in mean COP variables (velocity and displacement) between pooled NSCLBP and healthy subjects. However, the subjects were reclassified into AEP, FP and healthy groups and the results showed a significant difference in mean COP velocity in the PM direction between AEP and FP subjects (p=0.048), and between AEP and healthy subjects (p=0.024). Conclusions: The findings in this study highlight the heterogeneity of the individuals with NSCLBP and the importance of identifying the homogenous subgroups. Individuals with AEP and FP experience deficits in dynamic postural control compared to healthy controls. In addition, the findings of this study support the concept of the Multidimensional Classification System.

• 융합신호처리학회논문지
• /
• 제24권4호
• /
• pp.186-191
• /
• 2023

데이터 처리 기술은 의사결정을 위해 중요한 역할을 하며, 데이터 결측값 및 이상값 처리, 예측, 추천 모델 등이 포함 된다. 이는 모든 과정과 결과의 타당성, 신뢰성, 정확성에 대한 명확한 설명이 필요하다. 또한 의사결정트리, 추론 등을 이용한 설명가능한 모델을 통해 데이터의 문제를 해결하고, 다양한 유형의 학습을 고려하여 모델 경량화를 진행할 필요가 있다. 육하원칙을 적용한 다중 계층 마이닝 분류 방법은 데이터 전처리 후 트랜잭션에서 빈번하게 발생하는 변수와 속성 간의 다차원 관계를 발견하는 방법이다. 이는 트랜잭션에서 마이닝을 이용하여 유의미한 관계를 발견하고, 회귀분석을 통해 데이터를 모델링 하는 방법을 설명한다. 이에따라 확장 가능한 모델과 로지스틱 회귀모델을 개발하고, 데이터 정제, 관련성 분석, 데이터 변환, 데이터 증강을 통해 클래스 레이블을 생성하여 설명가능한 의사결정을 위한 미이닝 기술을 제안한다.

• 지능정보연구
• /
• 제29권3호
• /
• pp.57-78
• /
• 2023

2019년 11월 중국 우한시에서 발병한 코로나19는 2020년 중국을 넘어 세계로 퍼져나가 2020년 3월에는 전 세계적으로 확산되었다. 코로나19와 같이 전염성이 강한 바이러스는 예방과 확진시 적극적인 치료도 중요하지만 우선 전파 속도가 빠른 바이러스인 점을 감안할 때, 확진 사실을 재빠르게 파악하여 전파를 차단하는 것이 더욱 중요하다. 그러나 감염여부를 확인하기 위한 PCR검사는 비용과 시간이 많이 소요되고, 자가키트검사 또한 접근성은 쉽지만 매번 수시로 받기에는 키트의 가격이 부담이 될 수밖에 없는 실정이다. 이러한 상황에서 기침 소리를 기반으로 코로나19 양성 여부를 판단할 수 있게 된다면 누구나 쉽게 언제, 어디서든 확진 여부를 체크할 수 있어 신속성과 경제성 측면에서 큰 장점을 가질 수 있을 것이다. 따라서 본 연구는 기침 소리를 기반으로 코로나19 확진 여부를 식별할 수 있는 분류 모델을 개발하는 것을 목적으로 하였다. 이를 위해, 본 연구에서는 먼저 MFCC, Mel-Spectrogram, Spectral contrast, Spectrogram 등을 통해 기침 소리를 벡터화 하였다. 이 때, 기침 소리의 품질을 위해 SNR을 통해 잡음이 많은 데이터는 삭제하였고, chunk를 통해 음성 파일에서 기침 소리만 추출하였다. 이후, 추출된 기침 소리의 feature를 이용하여 코로나 양성과 음성을 분류하기 위한 모델을 구축하였으며, XGBoost, LightGBM, FCNN 알고리즘을 통해 모델 학습을 수행하고 각 알고리즘별 성능을 비교하였다. 또한, 기침 소리를 다차원 벡터로 변환한 경우와, 이미지로 변환한 경우에 대해 모델 성능에 대한 비교 실험을 수행하였다. 실험 결과, 건강상태에 대한 기본정보와 기침 소리를 MFCC, Mel-Spectogram, Spectral contrast, 그리고 Spectrogram을 통해 다차원 벡터로 변환한 feature를 모두 활용한 LightGBM 모델이 0.74의 가장 높은 정확도를 보였다.

• 환경영향평가
• /
• 제26권2호
• /
• pp.160-170
• /
• 2017

본 연구는 2006년부터 2012년까지 수행된 제3차 전국자연환경조사 포유류 데이터(70,562개)를 활용하여 국내에서 서식하는 포유류의 서식지 유형을 클러스터링하고 서식지 유형에 나타나는 종의 특징을 파악하고자 하였다. 제3차 전국자연환경조사의 야장에 기록된 서식지 유형 중에서 15개의 키워드를 뽑아 재분류하여 포유류 서식지유형을 통계 분석하였다. 서식지 유형 군집분석에서는 30회 이상 기록된 14개의 서식지 유형을 대상으로 비계층적 클러스터 분석(k 평균 클러스터 분석), 계층적 클러스터 분석, 비계량형 다차원척도법을 시행하였다. 2006년에서 2012년까지 전국에서 수집된 제3차 전국자연환경조사를 통해 확인된 포유류는 총 7목 16과 39종이었다. 서식지 유형에 대한 분류는 11개로 클러스터를 분류했을 때 단순구조지수가 가장 높았다(ssi = 0.07). 계층적 클러스터 분석으로 서식지 유형들 간의 유사성과 위계를 확인해 본 결과, 포유류에게는 주거지가 가장 차별된 서식지 유형이었고, 그 다음은 하천과 해안이 병합된 클러스터였다. 비계량형 다차원척도 분석 결과, 포유류에게 가장 차별된 서식지유형인 주거지의 경우 생쥐와 집쥐 두 종이 제한적으로 나타났으며, 해안과 하천의 경우 수달이 제한적으로 나타났다. 연구결과를 종합해보면, 포유류의 서식지 유형은 크게 산림을 주요 서식지와 이동경로로 이용하는 산림형과, 물을 주요 서식지로 이용하는 하천형, 주거지 인근에서 서식하는 주거형, 곡류나 씨앗을 주 먹이원으로 하는 저지대형 등 4가지로 구분할 수 있다.